metadata
license: mit
base_model: prajjwal1/bert-tiny
tags:
- generated_from_trainer
datasets:
- spark
metrics:
- accuracy
model-index:
- name: sentiment-model-saagie
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: spark
type: spark
config: '-904912027'
split: train
args: '-904912027'
metrics:
- name: Accuracy
type: accuracy
value: 0.7883333333333333
sentiment-model-saagie
This model is a fine-tuned version of prajjwal1/bert-tiny on the spark dataset. It achieves the following results on the evaluation set:
- Loss: 0.5440
- Accuracy: 0.7883
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5209 | 1.0 | 1500 | 0.4737 | 0.7917 |
0.3807 | 2.0 | 3000 | 0.5037 | 0.7883 |
0.3409 | 3.0 | 4500 | 0.5440 | 0.7883 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3